THE EXPLORATION OF CYP17A1 LIGAND SPACE BY THE QSAR MODEL

N. Boboriko, He Liying, Yaraslau U Dzichenka
{"title":"THE EXPLORATION OF CYP17A1 LIGAND SPACE BY THE QSAR MODEL","authors":"N. Boboriko, He Liying, Yaraslau U Dzichenka","doi":"10.46793/iccbi21.439b","DOIUrl":null,"url":null,"abstract":"Cytochrome P450 17A1 (CYP17A1) is a critically important enzyme in humans that catalyzes the formation of all endogenous androgens. This enzyme is often considered a molecular target for the development of novel high efficient drugs against prostate cancer. In the present work, the random forest algorithm was used to conduct a QSAR study on 370 CYP17A1 ligands with different structures that were collected from the literature and databases, and a QSAR model was created based on the five important descriptors screened out – 2D adjacency and distance matrix descriptors, 2D atom counts and bond counts and 3D surface area, volume and shape descriptors. The model was verified by the test set (accuracy, specificity, sensitivity, F-measure, MCC, and AUC were calculated). It was revealed that the hydrophobic properties of the vdW surface of the ligand have a significant contribution to the activity prediction. The hydrophobic effect of the molecules may be aroused by the presence of the hydrophobic groups or aromatic rings in the molecules. The created QSAR model shows that the molecules with more aromatic rings have better activity. The accuracy of the model on the test set was 84%, precision – 81%, sensitivity – 93%, specificity – 72%, F-measure – 0.87, MCC – 0.67, AUC – 0.88. The model has good robustness and predictive ability and can be used to screen and discover new highly active CYP17A1 inhibitors.","PeriodicalId":9171,"journal":{"name":"Book of Proceedings: 1st International Conference on Chemo and BioInformatics,","volume":"6 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Book of Proceedings: 1st International Conference on Chemo and BioInformatics,","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.46793/iccbi21.439b","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Cytochrome P450 17A1 (CYP17A1) is a critically important enzyme in humans that catalyzes the formation of all endogenous androgens. This enzyme is often considered a molecular target for the development of novel high efficient drugs against prostate cancer. In the present work, the random forest algorithm was used to conduct a QSAR study on 370 CYP17A1 ligands with different structures that were collected from the literature and databases, and a QSAR model was created based on the five important descriptors screened out – 2D adjacency and distance matrix descriptors, 2D atom counts and bond counts and 3D surface area, volume and shape descriptors. The model was verified by the test set (accuracy, specificity, sensitivity, F-measure, MCC, and AUC were calculated). It was revealed that the hydrophobic properties of the vdW surface of the ligand have a significant contribution to the activity prediction. The hydrophobic effect of the molecules may be aroused by the presence of the hydrophobic groups or aromatic rings in the molecules. The created QSAR model shows that the molecules with more aromatic rings have better activity. The accuracy of the model on the test set was 84%, precision – 81%, sensitivity – 93%, specificity – 72%, F-measure – 0.87, MCC – 0.67, AUC – 0.88. The model has good robustness and predictive ability and can be used to screen and discover new highly active CYP17A1 inhibitors.
qsar模型对cyp17a1配体空间的探索
细胞色素P450 17A1 (CYP17A1)在人类中是一种至关重要的酶,它催化所有内源性雄激素的形成。这种酶通常被认为是开发新型高效前列腺癌药物的分子靶标。本文利用随机森林算法对从文献和数据库中收集的370种不同结构的CYP17A1配体进行了QSAR研究,并基于筛选出的5个重要描述符——二维邻接矩阵和距离矩阵描述符、二维原子数和键数描述符以及三维表面积、体积和形状描述符建立了QSAR模型。通过测试集对模型进行验证(计算准确性、特异性、敏感性、F-measure、MCC和AUC)。结果表明,配体vdW表面的疏水性对活性预测有重要贡献。分子中的疏水基团或芳香环的存在可引起分子的疏水效应。建立的QSAR模型表明,芳香环越多的分子活性越好。模型在检验集中的准确度为84%,精密度为81%,灵敏度为93%,特异度为72%,F-measure为0.87,MCC为0.67,AUC为0.88。该模型具有良好的鲁棒性和预测能力,可用于筛选和发现新的高活性CYP17A1抑制剂。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信